© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116915
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inak
    -0.07
     at
    -0.07
     биз
    -0.07
     അവിടെ
    -0.07
    启动
    -0.06
     находится
    -0.06
    家族
    -0.06
    iname
    -0.06
     सर्वप्रथम
    -0.06
     Todos
    -0.06
    POSITIVE LOGITS
    !
    0.07
     so
    0.06
    就
    0.06
    !.
    0.06
    !!
    0.06
     taking
    0.06
     Sosa
    0.05
     !
    0.05
    !),
    0.05
    !"
    0.05
    Activations Density 0.003%

    No Known Activations